Get token usage statistics grouped by various dimensions
AI agents call get_token_stats to retrieve information from Claude Code History MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical usage statistics without side effects. It reads token usage data and presents it in various groupings, which is characteristic of a Read operation. There is no indication that it modifies data, executes code, or performs any destructive actions. The severity is low because disclosure of aggregate token statistics poses minimal risk to system integrity.
From the tool's definition Tool name is 'get_token_stats' and description states 'Get token usage statistics grouped by various dimensions' — a purely retrieval operation with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Get token usage statistics grouped by various dimensions. It is categorised as a Read tool in the Claude Code History MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Code History MCP server in PolicyLayer and add a rule for get_token_stats: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Code History MCP. Nothing to install.
get_token_stats is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_token_stats rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_token_stats. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_token_stats is provided by the Claude Code History MCP server (tim0120/claude-code-history-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →